Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1572 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.6682. Min Act: -0.0001

Data Index: 1620418 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.5419. Min Act: -0.0001

Data Index: 1610606 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3910. Min Act: -0.0001

Data Index: 1613160 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4481. Min Act: -0.0001

Data Index: 1630050 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3770. Min Act: -0.0001

Data Index: 1581162 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3353. Min Act: -0.0001

Data Index: 1644476 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.4230. Min Act: -0.0001

Data Index: 1590645 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.3152. Min Act: -0.0001

Data Index: 1443324 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2702. Min Act: -0.0001

Data Index: 1468801 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2476. Min Act: -0.0001

Data Index: 1383377 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2829. Min Act: -0.0001

Data Index: 1654843 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2366. Min Act: -0.0001

Data Index: 1543339 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2138. Min Act: -0.0001

Data Index: 1515517 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.2082. Min Act: -0.0001

Data Index: 1411866 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1849. Min Act: -0.0001

Data Index: 1512347 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1567480 (Python Code)

Max Activating Token Index: 582

Text #16

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1822. Min Act: -0.0001

Data Index: 1536613 (Python Code)

Max Activating Token Index: 275

Text #17

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1436. Min Act: -0.0001

Data Index: 1389694 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1405. Min Act: -0.0001

Data Index: 1468535 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 1.6682. Min Range: -1.6682

Max Act: 1.1245. Min Act: -0.0001

Data Index: 1655649 (Python Code)

Max Activating Token Index: 308